Jan Eichhorn

Learn More
The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and people. Twelve teams entered the challenge. In this chapter we provide(More)
Fatty acid composition and cholesterol content of muscle and adipose tissue from mature cows (N = 101) representing 15 breeds and crosses were determined. An initial group of cows was slaughtered after being fed slightly above the maintenance level for 2 wk; the remaining cows were fed either at the maintenance level or ad libitum for 84 d, then(More)
Fatty acid composition of total lipid extracts of muscle and adipose samples from crossbred bulls (N = 34) and steers (N = 35) was determined by gas-liquid chromatography. Samples of semitendinosus, triceps brachii and longissimus muscle and of subcutaneous and perinephric adipose tissue were excised from the right side of each carcass. In addition,(More)
Orientation selectivity is the most striking feature of simple cell coding in V1 that has been shown to emerge from the reduction of higher-order correlations in natural images in a large variety of statistical image models. The most parsimonious one among these models is linear Independent Component Analysis (ICA), whereas second-order decorrelation(More)
We report and compare the performance of different learning algorithms based on data from cortical recordings. The task is to predict the orientation of visual stimuli from the activity of a population of simultaneously recorded neurons. We compare several ways of improving the coding of the input (i.e., the spike data) as well as of the output (i.e., the(More)
In this thesis we are concerned with the application of supervised learning methods to two problems of rather different nature – one originating from computational neuro-science, the other one from computer vision. The kernel algorithms that will be used allow classification of complex objects that need not to be elements of a Euclidean vector space. For(More)
Orientation selectivity is the most striking feature of simple cell coding in V1 which has been shown to emerge from the reduction of higher-order correlations in natural images in a large variety of statistical image models. The most parsimonious one among these models is linear Independent Component Analysis (ICA), whereas second-order decorrelation(More)
In this paper we are concerned with the optimal combination of features of possibly different types for detection and estimation tasks in machine vision. We propose to combine features such that the resulting classifier maximizes the margin between classes. In contrast to existing approaches which are non-convex and/or generative we propose to use a(More)
Cholesterol content (mg/100g wet weight) of muscle and adipose tissue from crossbred bulls (N = 34) and steers (N = 35) was determined by spectrophotometry. Sampling site effects were highly significant, with subcutaneous adipose tissue (101·7) and perinephric adipose tissue (89·7) containing the most cholesterol, and longissimus muscle (58·3) containing(More)